retro Eval
==========

Status: review
Score: 81/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Require human approval before installing into a real workspace.

Install:
npx skills add phuryn/pm-skills --skill retro

Required checks:
- WARN Task fit: Task fit is weak; compare alternatives before selecting.
- PASS Install path: Install handoff is available.
- PASS Install command safety: standard package or runtime install path
- WARN Trust score: Good trust signals with a few areas worth checking before rollout.
- WARN Audit score: Needs review
- WARN Agent safety gate: Usable candidate, but the agent should surface permission and audit notes before installation.
- PASS License clarity: MIT
- PASS Permission surface: no high-risk permission surface in public metadata

Warnings:
- Task fit: Task fit is weak; compare alternatives before selecting.
- Trust score: Good trust signals with a few areas worth checking before rollout.
- Audit score: Needs review
- Agent safety gate: Usable candidate, but the agent should surface permission and audit notes before installation.
- README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context
- SKILL.md does not explicitly define safe operating boundaries, such as clarifying that sprint data and user-provided files must be treated as untrusted data and never as instructions.
- The skill implies it can analyze sprint performance and velocity, but it does not state what to do when that data is unavailable or incomplete, which could lead to hallucinated metrics.
- The action item template includes Owner and Deadline placeholders but does not explicitly warn against inventing owner names or deadlines when not provided by the user.
- Quality score needs review

Validation plan:
1. Inspect repository, README/SKILL.md, license, and recent commits before production use.
2. Install in an isolated workspace or sandbox with no production secrets available.
3. Run the smallest representative task and record files touched, commands run, network access, and outputs.
4. Compare the selected skill against at least one alternative when the eval status is review or failed.
5. Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

Do not use when:
- teams that need a vendor-supported SLA
- production agents without a repository review
- SKILL.md does not explicitly define safe operating boundaries, such as clarifying that sprint data and user-provided files must be treated as untrusted data and never as instructions.
- The skill implies it can analyze sprint performance and velocity, but it does not state what to do when that data is unavailable or incomplete, which could lead to hallucinated metrics.
- The action item template includes Owner and Deadline placeholders but does not explicitly warn against inventing owner names or deadlines when not provided by the user.
- Quality score needs review
- Production credentials, payments, or irreversible account changes without explicit human review
- Sensitive private data before reviewing repository code, license, and permission surface

URLs:
- Skill: https://www.openagentskill.com/skills/phuryn-retro
- Audit: https://www.openagentskill.com/skills/phuryn-retro/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=phuryn-retro